Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.3/238652

Title

Artificial Neural Networks (ANN) modelling of spring rainfall using dual-climate indices for Victoria, Australia

Author(s)

Mekanik, F.;  Imteaz, M.

Abstract

Australian rainfall is affected by key modes of complex climate variables such as El Nino-Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD) and the Southern Annular Mode (SAM). Many researchers have tried to establish the effects of these large-scale climate indices on the rainfall of different parts of Australia, particularly Western Australia, New South Wales, Queensland and Victoria. Unlike the other regions, no clear relationship can be found between each individual large-scale climate mode and Victorian rainfall. Past studies considering Victorian rainfall predictability could achieve a maximum of 30% correlation. This study looks into the lagged-time effect of these modes on Victorian spring rainfall. On the other hand, few attempts have been made to establish the combined effect of these indices on rainfall in order to develop a better model for predictions. Since rainfall is a complicated atmospheric phenomenon, linear techniques might not be sufficient to capture its characteristics. This research attempts to find a nonlinear relationship between the Victorian rainfall and the lagged-indices affecting the region using Artificial Neural Networks (ANN). ANN is known for its ability to map between the input variables and output variable without a prior in-depth knowledge of mechanisms. It was discovered that ANN modelling is able to provide higher correlations using the lagged-indices to forecast spring rainfall in compared to linear methods. This study found that predicting spring rainfall using lagged IOD index with ANN can achieve 99% correlation. ENSO did not prove to be as effective as IOD. This method can be used for other parts of Australia to establish a stronger relationship between rainfall and large scale climate modes which could not be established by linear methods.

Publication type

Conference paper

Research centre

Swinburne University of Technology. Faculty of Engineering and Industrial Sciences

Source

Proceedings of the 34th Hydrology and Water Resources Symposium (HWRS 2012), Sydney, New South Wales, Australia, 19-22 November 2012, pp. 1289-1297

Publication year

2012

Keyword(s)

Artificial Neural Networks;  Australia;  Climate indices;  Climate modes;  Climate patterns;  El Nino-Southern Oscillation;  Indian Ocean Dipole;  Rainfall;  Southern Annular Mode;  Spring

Publisher

Engineers Australia

ISBN

9781922107626, 192210762X

Publisher URL

http://www.hwrs2012.org.au/

Copyright

Copyright © 2012 Engineers Australia.

Peer reviewed